Model save

README.md

@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.46.3
+- PEFT 0.14.0
+- Transformers 4.48.0
 - Pytorch 2.5.1+cu124
-- Datasets 3.1.0
-- Tokenizers 0.20.3
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -6,6 +6,8 @@
   },
   "base_model_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": "gaussian",
@@ -14,6 +16,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 8,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -23,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
+    "o_proj",
     "q_proj",
+    "down_proj",
+    "gate_proj",
     "v_proj",
-    "o_proj",
-    "k_proj",
-    "down_proj"
+    "up_proj",
+    "k_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f14cfeb86f525c2d1a4aeaa033490f7e1ced1c0f435389eb0e068828e6d6ee1
+oid sha256:9d09d6982714d63cd8e1277590f3affdb5f96b55ccbd3a278a4b93b00a5fca2d
 size 125866776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f1f6555d4e3957c8a26fdd263d26eedd9536252cc21824452078c59e0df054
+oid sha256:0d676095c6c987594d96377e5143e9311465f2a788c9f1a522156b61485e9264
 size 5304